Update readme for LightX2V infer.

README.md

@@ -155,6 +155,7 @@ We recommend the following inference frameworks to serve the model:
 
 - [SGLang](https://docs.sglang.io/) - see [cookbook](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3-Image)
 - [vLLM-Omni](https://github.com/vllm-project/vllm-omni) - see [vllm-omni recipe](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3-Image)
+- [LightX2V](https://github.com/ModelTC/LightX2V) - see [Usage guide](https://github.com/ModelTC/LightX2V/tree/main/scripts/minimax_h3_image)
 - [diffusers](https://github.com/huggingface/diffusers) - see [diffusers docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_h3_image)
 - [ComfyUI](https://github.com/Comfy-Org/ComfyUI) - see [Comfy tutorial](https://docs.comfy.org/tutorials/image/minimax/minimax-h3-image); use [T2I template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_minimax_h3_image_t2i.json) / [Edit template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_minimax_h3_image_edit.json)
 
@@ -200,6 +201,39 @@ sglang serve --model-path MiniMaxAI/MiniMax-H3-Image --host 0.0.0.0 --port 30000
   --num-gpus 4 --ulysses-degree 4
 ```
 
+#### LightX2V Deployment
+
+See the [LightX2V MiniMax-H3-Image guide](https://github.com/ModelTC/LightX2V/tree/main/scripts/minimax_h3_image) for complete usage instructions.
+
+Update lightx2v_path, model_path, and GPU settings in the cache-generation and server startup scripts. Run the following commands from the LightX2V repository root.
+
+First, generate the AdaLN cache:
+
+```bash
+bash tools/cache_minimax_h3_adaln/run_cache_minimax_h3_image_adaln.sh
+```
+
+Skip this step if a matching cache already exists. The same cache can be reused for single-GPU and multi-GPU serving.
+
+Start the server on one GPU:
+
+```bash
+bash scripts/minimax_h3_image/server/start_server.sh
+```
+
+For lower latency, start the server on four GPUs with sequence parallelism:
+
+```bash
+bash scripts/minimax_h3_image/server/start_server_sp4.sh
+```
+
+After model loading, send a request from another terminal:
+
+```bash
+python scripts/minimax_h3_image/server/post_t2i.py
+python scripts/minimax_h3_image/server/post_i2i.py
+```
+
 #### Request parameters
 
 Text-to-image requests are JSON sent to `/v1/images/generations`. Image editing requests send